On Wed, Nov 08, 2023 at 12:30:39AM +0530, ank...@nvidia.com wrote:
> From: Ankit Agrawal <ank...@nvidia.com>
>
> ACPI spec provides a scheme to associate "Generic Initiators" [1]
> (e.g. heterogeneous processors and accelerators, GPUs, and I/O devices with
> integrated compute or DMA engines GPUs) with Proximity Domains. This is
> achieved using Generic Initiator Affinity Structure in SRAT. During bootup,
> Linux kernel parse the ACPI SRAT to determine the PXM ids and create a NUMA
> node for each unique PXM ID encountered. Qemu currently do not implement
> these structures while building SRAT.
>
> Add GI structures while building VM ACPI SRAT. The association between
> devices and nodes are stored using acpi-generic-initiator object. Lookup
> presence of all such objects and use them to build these structures.
>
> The structure needs a PCI device handle [2] that consists of the device BDF.
> The vfio-pci device corresponding to the acpi-generic-initiator object is
> located to determine the BDF.
>
> [1] ACPI Spec 6.5, Section 5.2.16.6
> [2] ACPI Spec 6.5, Table 5.66
>
> Signed-off-by: Ankit Agrawal <ank...@nvidia.com>
> ---
> hw/acpi/acpi-generic-initiator.c | 79 ++++++++++++++++++++++++
> hw/arm/virt-acpi-build.c | 3 +
> include/hw/acpi/acpi-generic-initiator.h | 21 +++++++
> 3 files changed, 103 insertions(+)
>
> diff --git a/hw/acpi/acpi-generic-initiator.c
> b/hw/acpi/acpi-generic-initiator.c
> index 0699c878e2..6d0a8fd818 100644
> --- a/hw/acpi/acpi-generic-initiator.c
> +++ b/hw/acpi/acpi-generic-initiator.c
> @@ -78,3 +78,82 @@ static void acpi_generic_initiator_class_init(ObjectClass
> *oc, void *data)
> object_class_property_add_str(oc, ACPI_GENERIC_INITIATOR_NODELIST_PROP,
> NULL, acpi_generic_initiator_set_nodelist);
> }
> +
> +static int acpi_generic_initiator_list(Object *obj, void *opaque)
> +{
> + GSList **list = opaque;
> +
> + if (object_dynamic_cast(obj, TYPE_ACPI_GENERIC_INITIATOR)) {
> + *list = g_slist_append(*list, ACPI_GENERIC_INITIATOR(obj));
> + }
> +
> + object_child_foreach(obj, acpi_generic_initiator_list, opaque);
> + return 0;
> +}
> +
> +/*
> + * Identify Generic Initiator objects and link them into the list which is
> + * returned to the caller.
> + *
> + * Note: it is the caller's responsibility to free the list to avoid
> + * memory leak.
> + */
> +static GSList *acpi_generic_initiator_get_list(void)
> +{
> + GSList *list = NULL;
> +
> + object_child_foreach(object_get_root(), acpi_generic_initiator_list,
> &list);
> + return list;
> +}
> +
> +/*
> + * ACPI spec, Revision 6.5
we normally just say ACPI 6.5 even though a couple of places are more
verbose.
> + * 5.2.16.6 Generic Initiator Affinity Structure
> + */
> +static
> +void build_srat_generic_pci_initiator_affinity(GArray *table_data, int node,
> + PCIDeviceHandle *handle)
> +{
> + uint8_t index;
> +
> + build_append_int_noprefix(table_data, 5, 1); /* Type */
> + build_append_int_noprefix(table_data, 32, 1); /* Length */
> + build_append_int_noprefix(table_data, 0, 1); /* Reserved */
> + build_append_int_noprefix(table_data, 1, 1); /* Device Handle Type */
> + build_append_int_noprefix(table_data, node, 4); /* Proximity Domain */
> + build_append_int_noprefix(table_data, handle->segment, 2);
> + build_append_int_noprefix(table_data, handle->bdf, 2);
> +
> + /* Reserved */
> + for (index = 0; index < 12; index++) {
> + build_append_int_noprefix(table_data, handle->res[index], 1);
> + }
> +
> + build_append_int_noprefix(table_data, GEN_AFFINITY_ENABLED, 4); /* Flags
> */
> + build_append_int_noprefix(table_data, 0, 4); /* Reserved */
> +}
> +
> +void build_srat_generic_pci_initiator(GArray *table_data)
> +{
> + GSList *gi_list, *list = acpi_generic_initiator_get_list();
> + for (gi_list = list; gi_list; gi_list = gi_list->next) {
> + AcpiGenericInitiator *gi = gi_list->data;
> + Object *o;
> + uint16List *l;
> +
> + o = object_resolve_path_type(gi->device, TYPE_VFIO_PCI, NULL);
> + if (!o) {
> + continue;
> + }
> +
> + for (l = gi->nodelist; l; l = l->next) {
> + PCIDeviceHandle dev_handle = {0};
> + PCIDevice *pci_dev = PCI_DEVICE(o);
> + dev_handle.bdf = PCI_BUILD_BDF(pci_bus_num(pci_get_bus(pci_dev)),
> + pci_dev->devfn);
> + build_srat_generic_pci_initiator_affinity(table_data,
> + l->value, &dev_handle);
> + }
> + }
> + g_slist_free(list);
> +}
> diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c
> index 6b674231c2..bd53788cef 100644
> --- a/hw/arm/virt-acpi-build.c
> +++ b/hw/arm/virt-acpi-build.c
> @@ -58,6 +58,7 @@
> #include "migration/vmstate.h"
> #include "hw/acpi/ghes.h"
> #include "hw/acpi/viot.h"
> +#include "hw/acpi/acpi-generic-initiator.h"
>
> #define ARM_SPI_BASE 32
>
> @@ -558,6 +559,8 @@ build_srat(GArray *table_data, BIOSLinker *linker,
> VirtMachineState *vms)
> }
> }
>
> + build_srat_generic_pci_initiator(table_data);
> +
> if (ms->nvdimms_state->is_enabled) {
> nvdimm_build_srat(table_data);
> }
> diff --git a/include/hw/acpi/acpi-generic-initiator.h
> b/include/hw/acpi/acpi-generic-initiator.h
> index bb127b2541..545f46ade5 100644
> --- a/include/hw/acpi/acpi-generic-initiator.h
> +++ b/include/hw/acpi/acpi-generic-initiator.h
> @@ -26,4 +26,25 @@ typedef struct AcpiGenericInitiatorClass {
> ObjectClass parent_class;
> } AcpiGenericInitiatorClass;
>
> +/*
> + * ACPI 6.5: Table 5-68 Flags - Generic Initiator
> + */
> +typedef enum {
> + GEN_AFFINITY_NOFLAGS = 0,
> + GEN_AFFINITY_ENABLED = (1 << 0),
> + GEN_AFFINITY_ARCH_TRANS = (1 << 1),
> +} GenericAffinityFlags;
Don't add these one-time use flags. They are impossible to match to
spec without reading and memorizing all of it. The way we do it in ACPI
code is this:
(1 << 0) /* [text matching ACPI spec verbatim ] */
this also means you will not add a ton of dead code just because it is
in the spec.
> +
> +/*
> + * ACPI 6.5: Table 5-66 Device Handle - PCI
In ACPI we document *earliest* spec version that includes this, not just
a random one you looked at. I checked 6.3 and it's there.
Pls find earliest one.
Same applies everywhere
> + * Device Handle definition
Again match spec text exactly. one line, and "definition" is not there.
> + */
> +typedef struct PCIDeviceHandle {
> + uint16_t segment;
> + uint16_t bdf;
> + uint8_t res[12];
what is this "res" and why do you need to pass it? It's always 0 isn't
it?
> +} PCIDeviceHandle;
> +
> +void build_srat_generic_pci_initiator(GArray *table_data);
> +
> #endif
> --
> 2.17.1
